import pandas as pds
datas = pds.read_csv('titanic.csv')
datas.head()
survived | pclass | sex | age | sibsp | parch | fare | embarked | class | who | adult_male | deck | embark_town | alive | alone | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | male | 22.0 | 1 | 0 | 7.2500 | S | Third | man | True | NaN | Southampton | no | False |
1 | 1 | 1 | female | 38.0 | 1 | 0 | 71.2833 | C | First | woman | False | C | Cherbourg | yes | False |
2 | 1 | 3 | female | 26.0 | 0 | 0 | 7.9250 | S | Third | woman | False | NaN | Southampton | yes | True |
3 | 1 | 1 | female | 35.0 | 1 | 0 | 53.1000 | S | First | woman | False | C | Southampton | yes | False |
4 | 0 | 3 | male | 35.0 | 0 | 0 | 8.0500 | S | Third | man | True | NaN | Southampton | no | True |
res=datas[['pclass', 'survived', 'sex']].groupby(['sex', 'pclass']).mean()
print(res)
survived sex pclass female 1 0.968085 2 0.921053 3 0.500000 male 1 0.368852 2 0.157407 3 0.135447
import matplotlib.pyplot as plt
res.plot(kind='bar')
plt.show()
res=datas[['pclass', 'survived', 'sex']].pivot_table(index = 'pclass', columns = 'sex')
res
survived | ||
---|---|---|
sex | female | male |
pclass | ||
1 | 0.968085 | 0.368852 |
2 | 0.921053 | 0.157407 |
3 | 0.500000 | 0.135447 |
import matplotlib.pyplot as plt
res.plot(kind='bar')
plt.show()
import numpy as np
import pandas as pds
import seaborn as sns
datas = sns.load_dataset('titanic') # csv de gitub
datas.columns
datas.head()
res = datas.pivot_table('survived',
aggfunc=np.mean,
index='class',
columns='sex')
res
sex | female | male |
---|---|---|
class | ||
First | 0.968085 | 0.368852 |
Second | 0.921053 | 0.157407 |
Third | 0.500000 | 0.135447 |
import matplotlib.pyplot as plt
res.plot(kind='bar')
plt.show()